OpenAI launches MedChemBench to test AI models on medicinal chemistry reasoning

Nov 20, 2026
GPT-6.2 Astra earned 84.5% of the credit across 99 problems, but OpenAI says the results do not show models can discover new drugs.

OpenAI has released MedChemBench, a benchmark that tests whether AI models can reason like medicinal chemists, the company said on 20 November. It asks models to connect a molecule's structure with experimental evidence to explain results, compare compounds and predict their properties.

The benchmark has 99 problems drawn from 117 published papers and patents, covering 761 molecular structures. Models get the context available at a point in a real research programme, such as the biological target, the compounds studied so far and selected findings, and are scored on reconstructing the molecules correctly, explaining the evidence, choosing compounds and predicting measured properties, with partial credit for close predictions.

OpenAI tested only its own GPT models. At the xhigh reasoning setting, GPT-6.2 Astra earned 84.5% of the available credit, against 83.3% for GPT-6 Astra, 82.0% for GPT-6.1 Sol and 58.2% for GPT-5.6 Sol. GPT-6 Astra earned 95.4% of the credit for reconstructing structures but only about half for selecting compounds and predicting numerical properties. In one example, GPT-5.6 Sol and GPT-5.6 Luna failed in all ten attempts to rebuild a molecule with an 18-atom ring that GPT-6 Astra got right every time.

OpenAI states the limits itself: the results do not show whether models can discover new drugs or improve laboratory decisions, prior exposure to the published sources cannot be ruled out, and each answer was a single attempt without tools, feedback or new experiments.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Life AI Weekly

Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.

Industry analysis

2025 Global Business Services Agenda: Gen AI Takes Center Stage

The Hackett Group

This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.